Related papers: SparseDFF: Sparse-View Feature Distillation for On…

Depth from focus (DFF) is one of the classical ill-posed inverse problems in computer vision. Most approaches recover the depth at each pixel based on the focal setting which exhibits maximal sharpness. Yet, it is not obvious how to…

Large pre-trained transformers have revolutionized artificial intelligence across various domains, and fine-tuning remains the dominant approach for adapting these models to downstream tasks due to the cost of training from scratch.…

We present NeSF, a method for producing 3D semantic fields from posed RGB images alone. In place of classical 3D representations, our method builds on recent work in implicit neural scene representations wherein 3D structure is captured by…

An open problem in mobile manipulation is how to represent objects and scenes in a unified manner so that robots can use both for navigation and manipulation. The latter requires capturing intricate geometry while understanding fine-grained…

With the prevalence of multimodal learning, camera-LiDAR fusion has gained popularity in 3D object detection. Although multiple fusion approaches have been proposed, they can be classified into either sparse-only or dense-only fashion based…

The ability to create high-quality 3D faces from a single image has become increasingly important with wide applications in video conferencing, AR/VR, and advanced video editing in movie industries. In this paper, we propose Face Diffusion…

We present Diff3F as a simple, robust, and class-agnostic feature descriptor that can be computed for untextured input shapes (meshes or point clouds). Our method distills diffusion features from image foundational models onto input shapes.…

Federated Learning (FL) enables multiple resource-constrained edge devices with varying levels of heterogeneity to collaboratively train a global model. However, devices with limited capacity can create bottlenecks and slow down model…

We introduce Structured 3D Features, a model based on a novel implicit 3D representation that pools pixel-aligned image features onto dense 3D points sampled from a parametric, statistical human mesh surface. The 3D points have associated…

Pre-trained diffusion models have demonstrated remarkable proficiency in synthesizing images across a wide range of scenarios with customizable prompts, indicating their effective capacity to capture universal features. Motivated by this,…

We propose DistillNeRF, a self-supervised learning framework addressing the challenge of understanding 3D environments from limited 2D observations in outdoor autonomous driving scenes. Our method is a generalizable feedforward model that…

In this paper, we present a deep learning based image feature extraction method designed specifically for face images. To train the feature extraction model, we construct a large scale photo-realistic face image dataset with ground-truth…

Reconstructing unbounded outdoor scenes from sparse outward-facing views poses significant challenges due to minimal view overlap. Previous methods often lack cross-scene understanding and their primitive-centric formulations overload local…

We present a framework, DISORF, to enable online 3D reconstruction and visualization of scenes captured by resource-constrained mobile robots and edge devices. To address the limited computing capabilities of edge devices and potentially…

Semantic understanding of 3D scenes is essential for robots to operate effectively and safely in complex environments. Existing methods for semantic scene reconstruction and semantic-aware novel view synthesis often rely on dense multi-view…

With the increasing deployment of facial image data across a wide range of applications, efficient compression tailored to facial semantics has become critical for both storage and transmission. While recent learning-based face image…

In this paper, we propose a novel approach to reconstruct 3D human body shapes based on a sparse set of RGBD frames using a single RGBD camera. We specifically focus on the realistic settings where human subjects move freely during the…

Sparse representation of 3D images is considered within the context of data reduction. The goal is to produce high quality approximations of 3D images using fewer elementary components than the number of intensity points in the 3D array.…

Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual…

We present a novel approach for recovering 3D shape and view dependent appearance from a few colored images, enabling efficient 3D reconstruction and novel view synthesis. Our method learns an implicit neural representation in the form of a…